© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4075
    Prev
    Next
    INDEX
    Explanations

    articles and determiners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     серви
    0.47
    ṕ
    0.44
     použí
    0.44
     serviço
    0.43
     रोहित
    0.43
     служба
    0.43
    ആര്‍
    0.42
    ഐ
    0.42
     एलईडी
    0.42
     ваших
    0.42
    POSITIVE LOGITS
     a
    0.69
     an
    0.62
    一个
    0.62
     একটি
    0.59
     một
    0.59
     isang
    0.59
     einen
    0.57
     ένα
    0.53
    a
    0.53
     sebuah
    0.50
    Activations Density 0.001%

    No Known Activations